QuailVadOptions

Options & Configuration · AiDotNet.Audio.VoiceActivity

Configuration options for the Quail VAD model.

Inheritance: ModelOptions → QuailVadOptions

For Beginners

Quail VAD detects when someone is speaking in audio - like a smart “is anyone talking right now?” detector. It’s designed to be small and fast enough to run on phones and embedded devices in real-time.

How It Works

Quail VAD (2024) is a lightweight voice activity detection model optimized for on-device deployment. It uses a compact CNN-RNN architecture with knowledge distillation from larger models, achieving high accuracy with minimal computational overhead.

Constructors

Constructor Summary
QuailVadOptions()

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } Gets or sets the ONNX runtime options.
double DropoutRate { get; set; } Gets or sets the dropout rate.
double LearningRate { get; set; } Gets or sets the learning rate.
double MinSilenceDuration { get; set; } Gets or sets the minimum silence duration in seconds.
double MinSpeechDuration { get; set; } Gets or sets the minimum speech duration in seconds.
double Threshold { get; set; } Gets or sets the speech detection threshold.
int FrameSizeMs { get; set; } Gets or sets the frame size in milliseconds.
int HiddenDim { get; set; } Gets or sets the hidden dimension.
int NumCNNLayers { get; set; } Gets or sets the number of CNN layers.
int RNNHiddenSize { get; set; } Gets or sets the RNN hidden size.
int SampleRate { get; set; } Gets or sets the audio sample rate in Hz.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.
string Variant { get; set; } Gets or sets the model variant.